find_files

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must convey behavioral traits. It mentions 'in-memory index' hinting at performance, but fails to disclose scope (e.g., which directories, case sensitivity) or side effects. As a safe read operation, this is adequate but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences front-load the core purpose and provide examples. Every word adds value; no redundancy. Slightly more structure (e.g., bullet points) would improve scannability but not necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no nested objects) and presence of an output schema, the description covers the essential behavior. It does not explain return values, but that is handled by the output schema. Slightly missing details on scope or performance characteristics, but overall complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description adds critical meaning to the 'pattern' parameter by explaining it supports glob patterns and providing specific examples ('*.py', 'README.md'). This compensates for the schema gap effectively.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool finds files matching glob patterns using an in-memory index. It uses specific verbs ('Find files') and resources ('files'), and distinguishes from siblings like 'search_code_advanced' by focusing on path/filename patterns rather than content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides pattern examples but lacks explicit guidance on when to use this tool versus alternatives like 'search_code_advanced' or 'refresh_index'. It does not specify context or exclusions, leaving the agent to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.